EuroFab

European Urban Fabric Classification Using Artificial Intelligence

Project introduction

structure of human settlements

temporal dimension

Why urban fabric

There are currently very few instances of detailed, consistent and scalable measurements of urban fabric, and virtually none of them provide insight into its change over time

EuroFab paves the road for a world where stakeholders, from local authorities to supranational organisations, are able to track and monitor the pattern of urban development in detail directly relevant for planning and at scale.

Direct contributions

  • Data-Driven Decision Making
  • Sustainable Urban Development
  • Climate Change Mitigation
  • Energy Efficiency and Renewable Energy
  • Nature-Based Solutions and Biodiversity
  • Remote sensing for land use
  • Computational and EO capability

High-level objectives

Strengthen UK and Czech national capability to exploit leading edge AI methods to integrate EO data and high-performance computing

Expand the integration and uptake of EO-derived information

Technical objectives

  • Specify, develop and validate innovative methods that can be scaled from laptop to HPC to integrate raster (satellite) and vector data in rich and explainable characterisations of urban fabric
  • Test the comparative performance of transformer-based (foundation) vision models against the baseline of convolution-based neural networks
  • Evaluate the selected vision models on two European regions
  • Develop open-source software, algorithms and open datasets that ensure the sustainability and usability of the project outputs beyond the initial funding period
  • Create the roadmap for a large-scale inference chain (i.e. covering all of Europe or parts of the globe) for the capability being developed

State of the Art

Proposed approach

Morphometrics

Satellite

How does it compare to existing products

Targeted users

First iteration

  • input datasets
  • envisaged system
  • Develop a space-time dataset of urban fabric in Great Britain
  • Develop a protocol, tools and models for homogenisation of morphometric classification.
  • Stakeholder consultation and co-production ensuring applicability and commercialisation of the data products [Claudia]